Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 4770
    Prev
    Next
    INDEX
    Explanations

    phrases or terms related to new opportunities, innovation, and growth

    oai_token-act-pair · gpt-3.5-turbo

    phrases or constructions that indicate relationships or connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    00007
    -0.69
    alion
    -0.66
    ivation
    -0.64
    ãĥ¼ãĥ³
    -0.64
    NES
    -0.63
    mie
    -0.63
    REF
    -0.62
    avia
    -0.61
    nis
    -0.61
    Ñĭ
    -0.60
    POSITIVE LOGITS
     various
    0.88
     varying
    0.80
     disasters
    0.66
     settlements
    0.65
     differing
    0.63
     religions
    0.62
     cities
    0.62
     civilizations
    0.62
     Various
    0.61
     assorted
    0.61
    Activations Density 0.572%

    No Known Activations